© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26293
    Prev
    Next
    INDEX
    Explanations

    full-time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åħĥå®Ŀ
    -0.10
    assin
    -0.09
    èĶ¼
    -0.09
    ENCE
    -0.09
    访è°Ī
    -0.08
    odes
    -0.08
    ษา
    -0.08
    ä¸īåĽĽ
    -0.08
    æĸ°ä¸ļæĢģ
    -0.08
    伤çĹħ
    -0.08
    POSITIVE LOGITS
    day
    0.09
    ä¸Ģ天
    0.09
    åįķ纯
    0.09
    çľģ份
    0.08
    çĶ¨æĪ·æıIJä¾Ľ
    0.08
     day
    0.08
    åľ¨åħ¨åĽ½
    0.08
     Prospect
    0.08
    pps
    0.08
    å°±è¿ij
    0.08
    Activations Density 0.009%

    No Known Activations